© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Jacobian LensNEW
    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-3-27B-IT
    5. 3-GEMMASCOPE-2-TRANSCODER-262K
    7. 89720
    Prev
    Next
    INDEX
    Explanations

    Viterbi algorithm

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2-27b-it/transcoder_all/layer_3_width_262k_l0_small_affine
    Prompts (Dashboard)
    238,145 prompts, 512 tokens each
    Dataset (Dashboard)
    lmsys + oasst1
    No Configuration Found
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    ون
    0.84
    ड
    0.74
    ll
    0.64
    며
    0.64
    lor
    0.63
    ৩
    0.62
    ب
    0.61
    य
    0.60
    nummer
    0.59
    ników
    0.58
    POSITIVE LOGITS
    arı
    0.68
    𝚊
    0.68
     a
    0.67
     участке
    0.67
    ു
    0.63
     свобод
    0.61
     can
    0.61
     средней
    0.60
     l
    0.59
     gradual
    0.59
    Activations Density 0.002%

    No Known Activations